zr-project-setup
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs routine project management tasks using specialized internal tools (
probe). No evidence of malicious intent, obfuscation, or security violations was found. - [COMMAND_EXECUTION]: The commands defined in
SKILL.mdutilize a specific CLI tool (probe) to create and update project records. These operations are consistent with the skill's stated purpose and use variables that are expected to be populated from internal 'idea' records. - [DATA_EXFILTRATION]: The skill does not access sensitive system files (e.g., SSH keys, AWS credentials) or perform network operations to untrusted domains. Messaging is restricted to an internal 'general' channel via the
probe messagetool. - [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guidelines, or extract system prompts were detected in the instructions or metadata.
Audit Metadata